Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5770 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1389. Min Range: -6.1389
Max Act: 6.0764. Min Act: -0.1700
Data Index: 73186 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1389. Min Range: -6.1389
Max Act: 6.1076. Min Act: -0.1700
Data Index: 6378506 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1389. Min Range: -6.1389
Max Act: 6.1076. Min Act: -0.1700
Data Index: 1407926 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1389. Min Range: -6.1389
Max Act: 6.1389. Min Act: -0.1700
Data Index: 4889937 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1389. Min Range: -6.1389
Max Act: 6.0764. Min Act: -0.1700
Data Index: 6253598 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1389. Min Range: -6.1389
Max Act: 6.0139. Min Act: -0.1700
Data Index: 1013830 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1389. Min Range: -6.1389
Max Act: 6.0451. Min Act: -0.1700
Data Index: 6778879 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1389. Min Range: -6.1389
Max Act: 6.0451. Min Act: -0.1700
Data Index: 2875724 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1389. Min Range: -6.1389
Max Act: 6.0139. Min Act: -0.1700
Data Index: 4986261 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1389. Min Range: -6.1389
Max Act: 6.0139. Min Act: -0.1700
Data Index: 4643098 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1389. Min Range: -6.1389
Max Act: 6.0139. Min Act: -0.1700
Data Index: 7514545 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1389. Min Range: -6.1389
Max Act: 5.9826. Min Act: -0.1700
Data Index: 1049222 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1389. Min Range: -6.1389
Max Act: 5.9826. Min Act: -0.1700
Data Index: 5735978 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1389. Min Range: -6.1389
Max Act: 5.9826. Min Act: -0.1700
Data Index: 2210161 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1389. Min Range: -6.1389
Max Act: 5.9826. Min Act: -0.1700
Data Index: 8686251 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1389. Min Range: -6.1389
Max Act: 5.9514. Min Act: -0.1700
Data Index: 6505961 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1389. Min Range: -6.1389
Max Act: 5.9514. Min Act: -0.1700
Data Index: 1633113 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1389. Min Range: -6.1389
Max Act: 5.9514. Min Act: -0.1700
Data Index: 1143460 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1389. Min Range: -6.1389
Max Act: 5.9201. Min Act: -0.1700
Data Index: 5735744 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1389. Min Range: -6.1389
Max Act: 5.9201. Min Act: -0.1700
Data Index: 2254537 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #19